def _get_time_bins(self, ax):
if not isinstance(ax, DatetimeIndex):
raise TypeError('axis must be a DatetimeIndex, but got '
'an instance of %r' % type(ax).__name__)
if len(ax) == 0:
binner = labels = DatetimeIndex(data=[],
freq=self.freq,
name=ax.name)
return binner, [], labels
first, last = ax.min(), ax.max()
first, last = _get_range_edges(first,
last,
self.freq,
closed=self.closed,
base=self.base)
tz = ax.tz
binner = labels = DatetimeIndex(freq=self.freq,
start=first.replace(tzinfo=None),
end=last.replace(tzinfo=None),
tz=tz,
name=ax.name)
# a little hack
trimmed = False
if (len(binner) > 2 and binner[-2] == last and self.closed == 'right'):
binner = binner[:-1]
trimmed = True
ax_values = ax.asi8
binner, bin_edges = self._adjust_bin_edges(binner, ax_values)
# general version, knowing nothing about relative frequencies
bins = lib.generate_bins_dt64(ax_values,
bin_edges,
self.closed,
hasnans=ax.hasnans)
if self.closed == 'right':
labels = binner
if self.label == 'right':
labels = labels[1:]
elif not trimmed:
labels = labels[:-1]
else:
if self.label == 'right':
labels = labels[1:]
elif not trimmed:
labels = labels[:-1]
if ax.hasnans:
binner = binner.insert(0, tslib.NaT)
labels = labels.insert(0, tslib.NaT)
# if we end up with more labels than bins
# adjust the labels
# GH4076
if len(bins) < len(labels):
labels = labels[:len(bins)]
return binner, bins, labels
def _concat_datetime(to_concat, axis=0, typs=None):
"""
provide concatenation of an datetimelike array of arrays each of which is a
single M8[ns], datetimet64[ns, tz] or m8[ns] dtype
Parameters
----------
to_concat : array of arrays
axis : axis to provide concatenation
typs : set of to_concat dtypes
Returns
-------
a single array, preserving the combined dtypes
"""
def convert_to_pydatetime(x, axis):
# coerce to an object dtype
# if dtype is of datetimetz or timezone
if x.dtype.kind == _NS_DTYPE.kind:
if getattr(x, 'tz', None) is not None:
x = x.asobject.values
else:
shape = x.shape
x = tslib.ints_to_pydatetime(x.view(np.int64).ravel())
x = x.reshape(shape)
elif x.dtype == _TD_DTYPE:
shape = x.shape
x = tslib.ints_to_pytimedelta(x.view(np.int64).ravel())
x = x.reshape(shape)
if axis == 1:
x = np.atleast_2d(x)
return x
if typs is None:
typs = get_dtype_kinds(to_concat)
# must be single dtype
if len(typs) == 1:
if 'datetimetz' in typs:
# datetime with no tz should be stored as "datetime" in typs,
# thus no need to care
# we require ALL of the same tz for datetimetz
tzs = set([str(x.tz) for x in to_concat])
if len(tzs) == 1:
from pandas.tseries.index import DatetimeIndex
new_values = np.concatenate(
[x.tz_localize(None).asi8 for x in to_concat])
return DatetimeIndex(new_values, tz=list(tzs)[0])
elif 'datetime' in typs:
new_values = np.concatenate([x.view(np.int64) for x in to_concat],
axis=axis)
return new_values.view(_NS_DTYPE)
elif 'timedelta' in typs:
new_values = np.concatenate([x.view(np.int64) for x in to_concat],
axis=axis)
return new_values.view(_TD_DTYPE)
# need to coerce to object
to_concat = [convert_to_pydatetime(x, axis) for x in to_concat]
return np.concatenate(to_concat, axis=axis)
if arg is None:
return arg
elif isinstance(arg, datetime):
return arg
elif isinstance(arg, Series):
values = _convert_f(arg.values)
return Series(values, index=arg.index, name=arg.name)
elif isinstance(arg, (np.ndarray, list)):
if isinstance(arg, list):
arg = np.array(arg, dtype='O')
if com.is_datetime64_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError, e:
try:
values, tz = lib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
return arg
try:
return _convert_f(arg)
except ValueError:
raise
return arg
try:
def _convert_listlike(arg, box, format):
if isinstance(arg, (list,tuple)):
arg = np.array(arg, dtype='O')
if com.is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError:
pass
return arg
arg = com._ensure_object(arg)
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = (
'%Y-%m-%dT%H:%M:%S.%f'.startswith(format) or
'%Y-%m-%d %H:%M:%S.%f'.startswith(format)
)
if format_is_iso8601:
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg)
except:
raise ValueError("cannot convert the input to '%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(
arg, format, coerce=coerce
)
except (tslib.OutOfBoundsDatetime):
if errors == 'raise':
raise
result = arg
except ValueError:
# Only raise this error if the user provided the
# datetime format, and not when it was inferred
if not infer_datetime_format:
raise
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(arg, raise_=errors == 'raise',
utc=utc, dayfirst=dayfirst,
coerce=coerce, unit=unit)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def test_cdaterange_holidays(self):
rng = cdate_range('2013-05-01', periods=3, holidays=['2013-05-01'])
xp = DatetimeIndex(['2013-05-02', '2013-05-03', '2013-05-06'])
self.assert_(xp.equals(rng))
def maybe_to_datetimelike(data, copy=False):
"""
return a DelegatedClass of a Series that is datetimelike
(e.g. datetime64[ns],timedelta64[ns] dtype or a Series of Periods)
raise TypeError if this is not possible.
Parameters
----------
data : Series
copy : boolean, default False
copy the input data
Returns
-------
DelegatedClass
"""
from pandas import Series
if not isinstance(data, Series):
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
index = data.index
name = data.name
orig = data if is_categorical_dtype(data) else None
if orig is not None:
data = orig.values.categories
if is_datetime64_dtype(data.dtype):
return DatetimeProperties(DatetimeIndex(data, copy=copy, freq='infer'),
index,
name=name,
orig=orig)
elif is_datetime64tz_dtype(data.dtype):
return DatetimeProperties(DatetimeIndex(data,
copy=copy,
freq='infer',
ambiguous='infer'),
index,
data.name,
orig=orig)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaProperties(TimedeltaIndex(data,
copy=copy,
freq='infer'),
index,
name=name,
orig=orig)
else:
if is_period_arraylike(data):
return PeriodProperties(PeriodIndex(data, copy=copy),
index,
name=name,
orig=orig)
if is_datetime_arraylike(data):
return DatetimeProperties(DatetimeIndex(data,
copy=copy,
freq='infer'),
index,
name=name,
orig=orig)
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
def to_datetime(arg, errors='ignore', dayfirst=False, utc=None, box=True,
format=None, coerce=False, unit='ns'):
"""
Convert argument to datetime
Parameters
----------
arg : string, datetime, array of strings (with possible NAs)
errors : {'ignore', 'raise'}, default 'ignore'
Errors are ignored by default (values left untouched)
dayfirst : boolean, default False
If True parses dates with the day first, eg 20/01/2005
Warning: dayfirst=True is not strict, but will prefer to parse
with day first (this is a known bug).
utc : boolean, default None
Return UTC DatetimeIndex if True (converting any tz-aware
datetime.datetime objects as well)
box : boolean, default True
If True returns a DatetimeIndex, if False returns ndarray of values
format : string, default None
strftime to parse time, eg "%d/%m/%Y"
coerce : force errors to NaT (False by default)
unit : unit of the arg (D,s,ms,us,ns) denote the unit in epoch
(e.g. a unix timestamp), which is an integer/float number
Returns
-------
ret : datetime if parsing succeeded
"""
from pandas import Timestamp
from pandas.core.series import Series
from pandas.tseries.index import DatetimeIndex
def _convert_listlike(arg, box):
if isinstance(arg, (list,tuple)):
arg = np.array(arg, dtype='O')
if com.is_datetime64_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError, e:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
return arg
arg = com._ensure_object(arg)
try:
if format is not None:
result = tslib.array_strptime(arg, format)
else:
result = tslib.array_to_datetime(arg, raise_=errors == 'raise',
utc=utc, dayfirst=dayfirst,
coerce=coerce, unit=unit)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError, e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def test_cdaterange(self):
rng = cdate_range('2013-05-01', periods=3)
xp = DatetimeIndex(['2013-05-01', '2013-05-02', '2013-05-03'])
self.assert_(xp.equals(rng))
def test_to_datetime_unit(self):
epoch = 1370745748
s = Series([epoch + t for t in range(20)])
result = to_datetime(s, unit='s')
expected = Series([Timestamp('2013-06-09 02:42:28') + timedelta(
seconds=t) for t in range(20)])
assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)]).astype(float)
result = to_datetime(s, unit='s')
expected = Series([Timestamp('2013-06-09 02:42:28') + timedelta(
seconds=t) for t in range(20)])
assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)] + [iNaT])
result = to_datetime(s, unit='s')
expected = Series([Timestamp('2013-06-09 02:42:28') + timedelta(
seconds=t) for t in range(20)] + [NaT])
assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)] + [iNaT]).astype(float)
result = to_datetime(s, unit='s')
expected = Series([Timestamp('2013-06-09 02:42:28') + timedelta(
seconds=t) for t in range(20)] + [NaT])
assert_series_equal(result, expected)
# GH13834
s = Series([epoch + t for t in np.arange(0, 2, .25)] +
[iNaT]).astype(float)
result = to_datetime(s, unit='s')
expected = Series([Timestamp('2013-06-09 02:42:28') + timedelta(
seconds=t) for t in np.arange(0, 2, .25)] + [NaT])
assert_series_equal(result, expected)
s = concat([Series([epoch + t for t in range(20)]
).astype(float), Series([np.nan])],
ignore_index=True)
result = to_datetime(s, unit='s')
expected = Series([Timestamp('2013-06-09 02:42:28') + timedelta(
seconds=t) for t in range(20)] + [NaT])
assert_series_equal(result, expected)
result = to_datetime([1, 2, 'NaT', pd.NaT, np.nan], unit='D')
expected = DatetimeIndex([Timestamp('1970-01-02'),
Timestamp('1970-01-03')] + ['NaT'] * 3)
tm.assert_index_equal(result, expected)
with self.assertRaises(ValueError):
to_datetime([1, 2, 'foo'], unit='D')
with self.assertRaises(ValueError):
to_datetime([1, 2, 111111111], unit='D')
# coerce we can process
expected = DatetimeIndex([Timestamp('1970-01-02'),
Timestamp('1970-01-03')] + ['NaT'] * 1)
result = to_datetime([1, 2, 'foo'], unit='D', errors='coerce')
tm.assert_index_equal(result, expected)
result = to_datetime([1, 2, 111111111], unit='D', errors='coerce')
tm.assert_index_equal(result, expected)
def tsplot(series, plotf, *args, **kwargs):
"""
Plots a Series on the given Matplotlib axes object
Parameters
----------
axes : Axes
series : Series
Notes
_____
Supports same args and kwargs as Axes.plot
"""
# Used inferred freq is possible, need a test case for inferred
freq = getattr(series.index, 'freq', None)
if freq is None and hasattr(series.index, 'inferred_freq'):
freq = series.index.inferred_freq
if isinstance(freq, DateOffset):
freq = freq.rule_code
else:
freq = frequencies.get_base_alias(freq)
freq = frequencies.to_calendar_freq(freq)
# Convert DatetimeIndex to PeriodIndex
if isinstance(series.index, DatetimeIndex):
idx = series.index.to_period(freq=freq)
series = Series(series.values, idx, name=series.name)
if not isinstance(series.index, PeriodIndex):
#try to get it to DatetimeIndex then to period
if series.index.inferred_type == 'datetime':
idx = DatetimeIndex(series.index).to_period(freq=freq)
series = Series(series.values, idx, name=series.name)
else:
raise TypeError('series argument to tsplot must have '
'DatetimeIndex or PeriodIndex')
if freq != series.index.freq:
series = series.asfreq(freq)
series = series.dropna()
style = kwargs.pop('style', None)
if 'ax' in kwargs:
ax = kwargs.pop('ax')
else:
ax = plt.gca()
# Specialized ts plotting attributes for Axes
ax.freq = freq
xaxis = ax.get_xaxis()
xaxis.freq = freq
xaxis.converter = DateConverter
ax.legendlabels = [kwargs.get('label', None)]
ax.view_interval = None
ax.date_axis_info = None
# format args and lot
args = _check_plot_params(series, series.index, freq, style, *args)
plotted = plotf(ax, *args, **kwargs)
format_dateaxis(ax, ax.freq)
# when adding a right axis (using add_yaxis), for some reason the
# x axis limits don't get properly set. This gets around the problem
xlim = ax.get_xlim()
if xlim[0] == 0.0 and xlim[1] == 1.0:
# if xlim still at default values, autoscale the axis
ax.autoscale_view()
left = series.index[0] #get_datevalue(series.index[0], freq)
right = series.index[-1] #get_datevalue(series.index[-1], freq)
ax.set_xlim(left, right)
return plotted
def makeDateIndex(k=10, freq='B'):
dt = datetime(2000, 1, 1)
dr = bdate_range(dt, periods=k, freq=freq)
return DatetimeIndex(dr)
def test_parsers(self):
# https://github.com/dateutil/dateutil/issues/217
import dateutil
yearfirst = dateutil.__version__ >= LooseVersion('2.5.0')
cases = {'2011-01-01': datetime.datetime(2011, 1, 1),
'2Q2005': datetime.datetime(2005, 4, 1),
'2Q05': datetime.datetime(2005, 4, 1),
'2005Q1': datetime.datetime(2005, 1, 1),
'05Q1': datetime.datetime(2005, 1, 1),
'2011Q3': datetime.datetime(2011, 7, 1),
'11Q3': datetime.datetime(2011, 7, 1),
'3Q2011': datetime.datetime(2011, 7, 1),
'3Q11': datetime.datetime(2011, 7, 1),
# quarterly without space
'2000Q4': datetime.datetime(2000, 10, 1),
'00Q4': datetime.datetime(2000, 10, 1),
'4Q2000': datetime.datetime(2000, 10, 1),
'4Q00': datetime.datetime(2000, 10, 1),
'2000q4': datetime.datetime(2000, 10, 1),
'2000-Q4': datetime.datetime(2000, 10, 1),
'00-Q4': datetime.datetime(2000, 10, 1),
'4Q-2000': datetime.datetime(2000, 10, 1),
'4Q-00': datetime.datetime(2000, 10, 1),
'00q4': datetime.datetime(2000, 10, 1),
'2005': datetime.datetime(2005, 1, 1),
'2005-11': datetime.datetime(2005, 11, 1),
'2005 11': datetime.datetime(2005, 11, 1),
'11-2005': datetime.datetime(2005, 11, 1),
'11 2005': datetime.datetime(2005, 11, 1),
'200511': datetime.datetime(2020, 5, 11),
'20051109': datetime.datetime(2005, 11, 9),
'20051109 10:15': datetime.datetime(2005, 11, 9, 10, 15),
'20051109 08H': datetime.datetime(2005, 11, 9, 8, 0),
'2005-11-09 10:15': datetime.datetime(2005, 11, 9, 10, 15),
'2005-11-09 08H': datetime.datetime(2005, 11, 9, 8, 0),
'2005/11/09 10:15': datetime.datetime(2005, 11, 9, 10, 15),
'2005/11/09 08H': datetime.datetime(2005, 11, 9, 8, 0),
"Thu Sep 25 10:36:28 2003": datetime.datetime(2003, 9, 25, 10,
36, 28),
"Thu Sep 25 2003": datetime.datetime(2003, 9, 25),
"Sep 25 2003": datetime.datetime(2003, 9, 25),
"January 1 2014": datetime.datetime(2014, 1, 1),
# GH 10537
'2014-06': datetime.datetime(2014, 6, 1),
'06-2014': datetime.datetime(2014, 6, 1),
'2014-6': datetime.datetime(2014, 6, 1),
'6-2014': datetime.datetime(2014, 6, 1),
'20010101 12': datetime.datetime(2001, 1, 1, 12),
'20010101 1234': datetime.datetime(2001, 1, 1, 12, 34),
'20010101 123456': datetime.datetime(2001, 1, 1, 12, 34, 56),
}
for date_str, expected in compat.iteritems(cases):
result1, _, _ = tools.parse_time_string(date_str,
yearfirst=yearfirst)
result2 = to_datetime(date_str, yearfirst=yearfirst)
result3 = to_datetime([date_str], yearfirst=yearfirst)
# result5 is used below
result4 = to_datetime(np.array([date_str], dtype=object),
yearfirst=yearfirst)
result6 = DatetimeIndex([date_str], yearfirst=yearfirst)
# result7 is used below
result8 = DatetimeIndex(Index([date_str]), yearfirst=yearfirst)
result9 = DatetimeIndex(Series([date_str]), yearfirst=yearfirst)
for res in [result1, result2]:
self.assertEqual(res, expected)
for res in [result3, result4, result6, result8, result9]:
exp = DatetimeIndex([pd.Timestamp(expected)])
tm.assert_index_equal(res, exp)
# these really need to have yearfist, but we don't support
if not yearfirst:
result5 = Timestamp(date_str)
self.assertEqual(result5, expected)
result7 = date_range(date_str, freq='S', periods=1,
yearfirst=yearfirst)
self.assertEqual(result7, expected)
# NaT
result1, _, _ = tools.parse_time_string('NaT')
result2 = to_datetime('NaT')
result3 = Timestamp('NaT')
result4 = DatetimeIndex(['NaT'])[0]
self.assertTrue(result1 is tslib.NaT)
self.assertTrue(result1 is tslib.NaT)
self.assertTrue(result1 is tslib.NaT)
self.assertTrue(result1 is tslib.NaT)
def test_parsers_dayfirst_yearfirst(self):
tm._skip_if_no_dateutil()
# OK
# 2.5.1 10-11-12 [dayfirst=0, yearfirst=0] -> 2012-10-11 00:00:00
# 2.5.2 10-11-12 [dayfirst=0, yearfirst=1] -> 2012-10-11 00:00:00
# 2.5.3 10-11-12 [dayfirst=0, yearfirst=0] -> 2012-10-11 00:00:00
# OK
# 2.5.1 10-11-12 [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00
# 2.5.2 10-11-12 [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00
# 2.5.3 10-11-12 [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00
# bug fix in 2.5.2
# 2.5.1 10-11-12 [dayfirst=1, yearfirst=1] -> 2010-11-12 00:00:00
# 2.5.2 10-11-12 [dayfirst=1, yearfirst=1] -> 2010-12-11 00:00:00
# 2.5.3 10-11-12 [dayfirst=1, yearfirst=1] -> 2010-12-11 00:00:00
# OK
# 2.5.1 10-11-12 [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00
# 2.5.2 10-11-12 [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00
# 2.5.3 10-11-12 [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00
# OK
# 2.5.1 20/12/21 [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00
# 2.5.2 20/12/21 [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00
# 2.5.3 20/12/21 [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00
# OK
# 2.5.1 20/12/21 [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00
# 2.5.2 20/12/21 [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00
# 2.5.3 20/12/21 [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00
# revert of bug in 2.5.2
# 2.5.1 20/12/21 [dayfirst=1, yearfirst=1] -> 2020-12-21 00:00:00
# 2.5.2 20/12/21 [dayfirst=1, yearfirst=1] -> month must be in 1..12
# 2.5.3 20/12/21 [dayfirst=1, yearfirst=1] -> 2020-12-21 00:00:00
# OK
# 2.5.1 20/12/21 [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
# 2.5.2 20/12/21 [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
# 2.5.3 20/12/21 [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00
import dateutil
is_lt_253 = dateutil.__version__ < LooseVersion('2.5.3')
# str : dayfirst, yearfirst, expected
cases = {'10-11-12': [(False, False,
datetime.datetime(2012, 10, 11)),
(True, False,
datetime.datetime(2012, 11, 10)),
(False, True,
datetime.datetime(2010, 11, 12)),
(True, True,
datetime.datetime(2010, 12, 11))],
'20/12/21': [(False, False,
datetime.datetime(2021, 12, 20)),
(True, False,
datetime.datetime(2021, 12, 20)),
(False, True,
datetime.datetime(2020, 12, 21)),
(True, True,
datetime.datetime(2020, 12, 21))]}
from dateutil.parser import parse
for date_str, values in compat.iteritems(cases):
for dayfirst, yearfirst, expected in values:
# odd comparisons across version
# let's just skip
if dayfirst and yearfirst and is_lt_253:
continue
# compare with dateutil result
dateutil_result = parse(date_str, dayfirst=dayfirst,
yearfirst=yearfirst)
self.assertEqual(dateutil_result, expected)
result1, _, _ = tools.parse_time_string(date_str,
dayfirst=dayfirst,
yearfirst=yearfirst)
# we don't support dayfirst/yearfirst here:
if not dayfirst and not yearfirst:
result2 = Timestamp(date_str)
self.assertEqual(result2, expected)
result3 = to_datetime(date_str, dayfirst=dayfirst,
yearfirst=yearfirst)
result4 = DatetimeIndex([date_str], dayfirst=dayfirst,
yearfirst=yearfirst)[0]
self.assertEqual(result1, expected)
self.assertEqual(result3, expected)
self.assertEqual(result4, expected)
def makeDateIndex(k):
dt = datetime(2000, 1, 1)
dr = bdate_range(dt, periods=k)
return DatetimeIndex(dr)
def test_dt_namespace_accessor(self):
# GH 7207, 11128
# test .dt namespace accessor
ok_for_base = ['year', 'month', 'day', 'hour', 'minute', 'second',
'weekofyear', 'week', 'dayofweek', 'weekday',
'dayofyear', 'quarter', 'freq', 'days_in_month',
'daysinmonth', 'is_leap_year']
ok_for_period = ok_for_base + ['qyear', 'start_time', 'end_time']
ok_for_period_methods = ['strftime', 'to_timestamp', 'asfreq']
ok_for_dt = ok_for_base + ['date', 'time', 'microsecond', 'nanosecond',
'is_month_start', 'is_month_end',
'is_quarter_start', 'is_quarter_end',
'is_year_start', 'is_year_end', 'tz',
'weekday_name']
ok_for_dt_methods = ['to_period', 'to_pydatetime', 'tz_localize',
'tz_convert', 'normalize', 'strftime', 'round',
'floor', 'ceil', 'weekday_name']
ok_for_td = ['days', 'seconds', 'microseconds', 'nanoseconds']
ok_for_td_methods = ['components', 'to_pytimedelta', 'total_seconds',
'round', 'floor', 'ceil']
def get_expected(s, name):
result = getattr(Index(s._values), prop)
if isinstance(result, np.ndarray):
if is_integer_dtype(result):
result = result.astype('int64')
elif not is_list_like(result):
return result
return Series(result, index=s.index, name=s.name)
def compare(s, name):
a = getattr(s.dt, prop)
b = get_expected(s, prop)
if not (is_list_like(a) and is_list_like(b)):
self.assertEqual(a, b)
else:
tm.assert_series_equal(a, b)
# datetimeindex
cases = [Series(date_range('20130101', periods=5), name='xxx'),
Series(date_range('20130101', periods=5, freq='s'),
name='xxx'),
Series(date_range('20130101 00:00:00', periods=5, freq='ms'),
name='xxx')]
for s in cases:
for prop in ok_for_dt:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.tz_localize('US/Eastern')
exp_values = DatetimeIndex(s.values).tz_localize('US/Eastern')
expected = Series(exp_values, index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
self.assertEqual(str(tz_result), 'US/Eastern')
freq_result = s.dt.freq
self.assertEqual(freq_result, DatetimeIndex(s.values,
freq='infer').freq)
# let's localize, then convert
result = s.dt.tz_localize('UTC').dt.tz_convert('US/Eastern')
exp_values = (DatetimeIndex(s.values).tz_localize('UTC')
.tz_convert('US/Eastern'))
expected = Series(exp_values, index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
# round
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.round('D')
expected = Series(pd.to_datetime(['2012-01-02', '2012-01-02',
'2012-01-01']), name='xxx')
tm.assert_series_equal(result, expected)
# round with tz
result = (s.dt.tz_localize('UTC')
.dt.tz_convert('US/Eastern')
.dt.round('D'))
exp_values = pd.to_datetime(['2012-01-01', '2012-01-01',
'2012-01-01']).tz_localize('US/Eastern')
expected = Series(exp_values, name='xxx')
tm.assert_series_equal(result, expected)
# floor
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.floor('D')
expected = Series(pd.to_datetime(['2012-01-01', '2012-01-01',
'2012-01-01']), name='xxx')
tm.assert_series_equal(result, expected)
# ceil
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.ceil('D')
expected = Series(pd.to_datetime(['2012-01-02', '2012-01-02',
'2012-01-02']), name='xxx')
tm.assert_series_equal(result, expected)
# datetimeindex with tz
s = Series(date_range('20130101', periods=5, tz='US/Eastern'),
name='xxx')
for prop in ok_for_dt:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.tz_convert('CET')
expected = Series(s._values.tz_convert('CET'),
index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
self.assertEqual(str(tz_result), 'CET')
freq_result = s.dt.freq
self.assertEqual(freq_result, DatetimeIndex(s.values,
freq='infer').freq)
# timedeltaindex
cases = [Series(timedelta_range('1 day', periods=5),
index=list('abcde'), name='xxx'),
Series(timedelta_range('1 day 01:23:45', periods=5,
freq='s'), name='xxx'),
Series(timedelta_range('2 days 01:23:45.012345', periods=5,
freq='ms'), name='xxx')]
for s in cases:
for prop in ok_for_td:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_td_methods:
getattr(s.dt, prop)
result = s.dt.components
self.assertIsInstance(result, DataFrame)
tm.assert_index_equal(result.index, s.index)
result = s.dt.to_pytimedelta()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.total_seconds()
self.assertIsInstance(result, pd.Series)
self.assertTrue(result.dtype == 'float64')
freq_result = s.dt.freq
self.assertEqual(freq_result, TimedeltaIndex(s.values,
freq='infer').freq)
# both
index = date_range('20130101', periods=3, freq='D')
s = Series(date_range('20140204', periods=3, freq='s'),
index=index, name='xxx')
exp = Series(np.array([2014, 2014, 2014], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.year, exp)
exp = Series(np.array([2, 2, 2], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.month, exp)
exp = Series(np.array([0, 1, 2], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.second, exp)
exp = pd.Series([s[0]] * 3, index=index, name='xxx')
tm.assert_series_equal(s.dt.normalize(), exp)
# periodindex
cases = [Series(period_range('20130101', periods=5, freq='D'),
name='xxx')]
for s in cases:
for prop in ok_for_period:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_period_methods:
getattr(s.dt, prop)
freq_result = s.dt.freq
self.assertEqual(freq_result, PeriodIndex(s.values).freq)
# test limited display api
def get_dir(s):
results = [r for r in s.dt.__dir__() if not r.startswith('_')]
return list(sorted(set(results)))
s = Series(date_range('20130101', periods=5, freq='D'), name='xxx')
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
s = Series(period_range('20130101', periods=5,
freq='D', name='xxx').asobject)
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_period + ok_for_period_methods))))
# 11295
# ambiguous time error on the conversions
s = Series(pd.date_range('2015-01-01', '2016-01-01',
freq='T'), name='xxx')
s = s.dt.tz_localize('UTC').dt.tz_convert('America/Chicago')
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
exp_values = pd.date_range('2015-01-01', '2016-01-01', freq='T',
tz='UTC').tz_convert('America/Chicago')
expected = Series(exp_values, name='xxx')
tm.assert_series_equal(s, expected)
# no setting allowed
s = Series(date_range('20130101', periods=5, freq='D'), name='xxx')
with tm.assertRaisesRegexp(ValueError, "modifications"):
s.dt.hour = 5
# trying to set a copy
with pd.option_context('chained_assignment', 'raise'):
def f():
s.dt.hour[0] = 5
self.assertRaises(com.SettingWithCopyError, f)
def _get_time_bins(self, ax):
if not isinstance(ax, DatetimeIndex):
raise TypeError('axis must be a DatetimeIndex, but got '
'an instance of %r' % type(ax).__name__)
if len(ax) == 0:
binner = labels = DatetimeIndex(data=[],
freq=self.freq,
name=ax.name)
return binner, [], labels
first, last = ax.min(), ax.max()
first, last = _get_range_edges(first,
last,
self.freq,
closed=self.closed,
base=self.base)
tz = ax.tz
# GH #12037
# use first/last directly instead of call replace() on them
# because replace() will swallow the nanosecond part
# thus last bin maybe slightly before the end if the end contains
# nanosecond part and lead to `Values falls after last bin` error
binner = labels = DatetimeIndex(freq=self.freq,
start=first,
end=last,
tz=tz,
name=ax.name)
# a little hack
trimmed = False
if (len(binner) > 2 and binner[-2] == last and self.closed == 'right'):
binner = binner[:-1]
trimmed = True
ax_values = ax.asi8
binner, bin_edges = self._adjust_bin_edges(binner, ax_values)
# general version, knowing nothing about relative frequencies
bins = lib.generate_bins_dt64(ax_values,
bin_edges,
self.closed,
hasnans=ax.hasnans)
if self.closed == 'right':
labels = binner
if self.label == 'right':
labels = labels[1:]
elif not trimmed:
labels = labels[:-1]
else:
if self.label == 'right':
labels = labels[1:]
elif not trimmed:
labels = labels[:-1]
if ax.hasnans:
binner = binner.insert(0, tslib.NaT)
labels = labels.insert(0, tslib.NaT)
# if we end up with more labels than bins
# adjust the labels
# GH4076
if len(bins) < len(labels):
labels = labels[:len(bins)]
return binner, bins, labels
def _convert_listlike(arg, box, format, name=None, tz=tz):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
# these are shortcutable
if is_datetime64tz_dtype(arg):
if not isinstance(arg, DatetimeIndex):
return DatetimeIndex(arg, tz=tz, name=name)
if utc:
arg = arg.tz_convert(None).tz_localize('UTC')
return arg
elif is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz=tz, name=name)
except ValueError:
pass
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
arg = getattr(arg, 'values', arg)
result = tslib.array_with_unit_to_datetime(arg,
unit,
errors=errors)
if box:
if errors == 'ignore':
from pandas import Index
return Index(result)
return DatetimeIndex(result, tz=tz, name=name)
return result
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, datetime, list, tuple, '
'1-d array, or Series')
arg = _ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = _format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, errors=errors)
except:
raise ValueError("cannot convert the input to "
"'%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg,
format,
exact=exact,
errors=errors)
except tslib.OutOfBoundsDatetime:
if errors == 'raise':
raise
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == 'raise':
raise
result = arg
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(
arg,
errors=errors,
utc=utc,
dayfirst=dayfirst,
yearfirst=yearfirst,
require_iso8601=require_iso8601)
if is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz=tz, name=name)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, name=name, tz=tz)
except (ValueError, TypeError):
raise e
def test_cdaterange_weekmask(self):
rng = cdate_range('2013-05-01',
periods=3,
weekmask='Sun Mon Tue Wed Thu')
xp = DatetimeIndex(['2013-05-01', '2013-05-02', '2013-05-05'])
self.assert_(xp.equals(rng))
def test_constructor_with_datetime_tz(self):
# 8260
# support datetime64 with tz
dr = date_range('20130101', periods=3, tz='US/Eastern')
s = Series(dr)
self.assertTrue(s.dtype.name == 'datetime64[ns, US/Eastern]')
self.assertTrue(s.dtype == 'datetime64[ns, US/Eastern]')
self.assertTrue(is_datetime64tz_dtype(s.dtype))
self.assertTrue('datetime64[ns, US/Eastern]' in str(s))
# export
result = s.values
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == 'datetime64[ns]')
exp = pd.DatetimeIndex(result)
exp = exp.tz_localize('UTC').tz_convert(tz=s.dt.tz)
self.assert_index_equal(dr, exp)
# indexing
result = s.iloc[0]
self.assertEqual(
result,
Timestamp('2013-01-01 00:00:00-0500', tz='US/Eastern', freq='D'))
result = s[0]
self.assertEqual(
result,
Timestamp('2013-01-01 00:00:00-0500', tz='US/Eastern', freq='D'))
result = s[Series([True, True, False], index=s.index)]
assert_series_equal(result, s[0:2])
result = s.iloc[0:1]
assert_series_equal(result, Series(dr[0:1]))
# concat
result = pd.concat([s.iloc[0:1], s.iloc[1:]])
assert_series_equal(result, s)
# astype
result = s.astype(object)
expected = Series(DatetimeIndex(s._values).asobject)
assert_series_equal(result, expected)
result = Series(s.values).dt.tz_localize('UTC').dt.tz_convert(s.dt.tz)
assert_series_equal(result, s)
# astype - datetime64[ns, tz]
result = Series(s.values).astype('datetime64[ns, US/Eastern]')
assert_series_equal(result, s)
result = Series(s.values).astype(s.dtype)
assert_series_equal(result, s)
result = s.astype('datetime64[ns, CET]')
expected = Series(date_range('20130101 06:00:00', periods=3, tz='CET'))
assert_series_equal(result, expected)
# short str
self.assertTrue('datetime64[ns, US/Eastern]' in str(s))
# formatting with NaT
result = s.shift()
self.assertTrue('datetime64[ns, US/Eastern]' in str(result))
self.assertTrue('NaT' in str(result))
# long str
t = Series(date_range('20130101', periods=1000, tz='US/Eastern'))
self.assertTrue('datetime64[ns, US/Eastern]' in str(t))
result = pd.DatetimeIndex(s, freq='infer')
tm.assert_index_equal(result, dr)
# inference
s = Series([
pd.Timestamp('2013-01-01 13:00:00-0800', tz='US/Pacific'),
pd.Timestamp('2013-01-02 14:00:00-0800', tz='US/Pacific')
])
self.assertTrue(s.dtype == 'datetime64[ns, US/Pacific]')
self.assertTrue(lib.infer_dtype(s) == 'datetime64')
s = Series([
pd.Timestamp('2013-01-01 13:00:00-0800', tz='US/Pacific'),
pd.Timestamp('2013-01-02 14:00:00-0800', tz='US/Eastern')
])
self.assertTrue(s.dtype == 'object')
self.assertTrue(lib.infer_dtype(s) == 'datetime')
# with all NaT
s = Series(pd.NaT, index=[0, 1], dtype='datetime64[ns, US/Eastern]')
expected = Series(pd.DatetimeIndex(['NaT', 'NaT'], tz='US/Eastern'))
assert_series_equal(s, expected)
def _convert_listlike(arg, box, format, name=None):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
# these are shortcutable
if com.is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg,
tz='utc' if utc else None,
name=name)
except ValueError:
pass
return arg
elif com.is_datetime64tz_dtype(arg):
if not isinstance(arg, DatetimeIndex):
return DatetimeIndex(arg, tz='utc' if utc else None)
if utc:
arg = arg.tz_convert(None)
return arg
elif format is None and com.is_integer_dtype(arg) and unit == 'ns':
result = arg.astype('datetime64[ns]')
if box:
return DatetimeIndex(result,
tz='utc' if utc else None,
name=name)
return result
arg = com._ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = (('%Y-%m-%dT%H:%M:%S.%f'.startswith(format)
or '%Y-%m-%d %H:%M:%S.%f'.startswith(format))
and format != '%Y')
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, errors=errors)
except:
raise ValueError(
"cannot convert the input to '%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg,
format,
exact=exact,
errors=errors)
except (tslib.OutOfBoundsDatetime):
if errors == 'raise':
raise
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == 'raise':
raise
result = arg
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(
arg,
errors=errors,
utc=utc,
dayfirst=dayfirst,
yearfirst=yearfirst,
freq=freq,
unit=unit,
require_iso8601=require_iso8601)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result,
tz='utc' if utc else None,
name=name)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, name=name, tz=tz)
except (ValueError, TypeError):
raise e
def test_parsers(self):
cases = {
'2011-01-01': datetime.datetime(2011, 1, 1),
'2Q2005': datetime.datetime(2005, 4, 1),
'2Q05': datetime.datetime(2005, 4, 1),
'2005Q1': datetime.datetime(2005, 1, 1),
'05Q1': datetime.datetime(2005, 1, 1),
'2011Q3': datetime.datetime(2011, 7, 1),
'11Q3': datetime.datetime(2011, 7, 1),
'3Q2011': datetime.datetime(2011, 7, 1),
'3Q11': datetime.datetime(2011, 7, 1),
# quarterly without space
'2000Q4': datetime.datetime(2000, 10, 1),
'00Q4': datetime.datetime(2000, 10, 1),
'4Q2000': datetime.datetime(2000, 10, 1),
'4Q00': datetime.datetime(2000, 10, 1),
'2000q4': datetime.datetime(2000, 10, 1),
'2000-Q4': datetime.datetime(2000, 10, 1),
'00-Q4': datetime.datetime(2000, 10, 1),
'4Q-2000': datetime.datetime(2000, 10, 1),
'4Q-00': datetime.datetime(2000, 10, 1),
'2000q4': datetime.datetime(2000, 10, 1),
'00q4': datetime.datetime(2000, 10, 1),
'2005': datetime.datetime(2005, 1, 1),
'2005-11': datetime.datetime(2005, 11, 1),
'2005 11': datetime.datetime(2005, 11, 1),
'11-2005': datetime.datetime(2005, 11, 1),
'11 2005': datetime.datetime(2005, 11, 1),
'200511': datetime.datetime(2020, 5, 11),
'20051109': datetime.datetime(2005, 11, 9),
'20051109 10:15': datetime.datetime(2005, 11, 9, 10, 15),
'20051109 08H': datetime.datetime(2005, 11, 9, 8, 0),
'2005-11-09 10:15': datetime.datetime(2005, 11, 9, 10, 15),
'2005-11-09 08H': datetime.datetime(2005, 11, 9, 8, 0),
'2005/11/09 10:15': datetime.datetime(2005, 11, 9, 10, 15),
'2005/11/09 08H': datetime.datetime(2005, 11, 9, 8, 0),
"Thu Sep 25 10:36:28 2003":
datetime.datetime(2003, 9, 25, 10, 36, 28),
"Thu Sep 25 2003": datetime.datetime(2003, 9, 25),
"Sep 25 2003": datetime.datetime(2003, 9, 25),
"January 1 2014": datetime.datetime(2014, 1, 1),
# GH 10537
'2014-06': datetime.datetime(2014, 6, 1),
'06-2014': datetime.datetime(2014, 6, 1),
'2014-6': datetime.datetime(2014, 6, 1),
'6-2014': datetime.datetime(2014, 6, 1),
}
for date_str, expected in compat.iteritems(cases):
result1, _, _ = tools.parse_time_string(date_str)
result2 = to_datetime(date_str)
result3 = to_datetime([date_str])
result4 = to_datetime(np.array([date_str], dtype=object))
result5 = Timestamp(date_str)
result6 = DatetimeIndex([date_str])[0]
result7 = date_range(date_str, freq='S', periods=1)
self.assertEqual(result1, expected)
self.assertEqual(result2, expected)
self.assertEqual(result3, expected)
self.assertEqual(result4, expected)
self.assertEqual(result5, expected)
self.assertEqual(result6, expected)
self.assertEqual(result7, expected)
# NaT
result1, _, _ = tools.parse_time_string('NaT')
result2 = to_datetime('NaT')
result3 = Timestamp('NaT')
result4 = DatetimeIndex(['NaT'])[0]
self.assertTrue(result1 is tslib.NaT)
self.assertTrue(result1 is tslib.NaT)
self.assertTrue(result1 is tslib.NaT)
self.assertTrue(result1 is tslib.NaT)
